返回全部动态

Worldwide Express 用 Amazon Bedrock 多智能体自动化货运异常

原标题:How Worldwide Express automated freight exceptions with Amazon Bedrock

AWS Machine Learning Blog一手来源商业质量 56

AI 摘要

Worldwide Express(ShipStation Global 旗下)与 AWS 及 LTM 合作,基于 Amazon Bedrock 构建多智能体 AI 方案,接入其运输管理系统 SpeedShip,自动处理 LTL 货运中的账单异常。系统由发票匹配、价格差异、附加费验证三个专用智能体组成,各自调用承运商知识库并保留人工审批环节。上线六个月后,活跃异常减少 75%,回款周期缩短 4 周,年节省 100 万美元,并带来一次性 1000 万美元自由现金流。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

How Worldwide Express automated freight exceptions with Amazon Bedrock Worldwide Express (part of ShipStation Global) had built something big: approximately $5 billion in systemwide revenue, over 75 less-than-truckload (LTL) carriers and more than 130,000 customers. But that same scale had a hidden cost. Every month, $15 million in free cash flow sat frozen, locked in billing exceptions no one had resolved yet. Each one had to be chased down by hand, carrier by carrier, with its own rules to che


发布时间:2026-10-31 01:32
抓取时间:2026-10-31 02:05
来源机构:AWS
阅读原文aws.amazon.com